This paper introduces a new video diffusion transformer called SANA-Video 2.0 that can generate high-quality videos efficiently, using a hybrid approach that combines linear attention with attention residuals. Practitioners might care about this paper because it presents a scalable and efficient method for generating high-resolution videos.
Firehose
Filtered to Papers, tagged “efficient video generation” · clear filters
Browse: People · Companies · Papers · Podcasts · Hacker News